Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1266 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.4061. Min Range: -3.4061

Max Act: 3.4061. Min Act: -0.0000

Data Index: 148959 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 3.4061. Min Range: -3.4061

Max Act: 3.3543. Min Act: -0.0000

Data Index: 740281 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 3.4061. Min Range: -3.4061

Max Act: 2.9398. Min Act: -0.0000

Data Index: 159364 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 3.4061. Min Range: -3.4061

Max Act: 2.4691. Min Act: -0.0000

Data Index: 1059761 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 3.4061. Min Range: -3.4061

Max Act: 2.6446. Min Act: -0.0000

Data Index: 740570 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 3.4061. Min Range: -3.4061

Max Act: 2.6887. Min Act: 0.0000

Data Index: 594695 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 3.4061. Min Range: -3.4061

Max Act: 2.6368. Min Act: -0.0000

Data Index: 202476 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 3.4061. Min Range: -3.4061

Max Act: 2.5790. Min Act: -0.0000

Data Index: 644858 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 3.4061. Min Range: -3.4061

Max Act: 2.4264. Min Act: -0.0000

Data Index: 552957 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 3.4061. Min Range: -3.4061

Max Act: 2.1461. Min Act: -0.0000

Data Index: 376328 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 3.4061. Min Range: -3.4061

Max Act: 2.2438. Min Act: -0.0000

Data Index: 521767 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 3.4061. Min Range: -3.4061

Max Act: 2.0527. Min Act: -0.0000

Data Index: 436609 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 3.4061. Min Range: -3.4061

Max Act: 2.4246. Min Act: -0.0000

Data Index: 649530 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 3.4061. Min Range: -3.4061

Max Act: 2.2753. Min Act: -0.0000

Data Index: 943487 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 3.4061. Min Range: -3.4061

Max Act: 2.3533. Min Act: -0.0000

Data Index: 458355 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 3.4061. Min Range: -3.4061

Max Act: 2.3275. Min Act: -0.0000

Data Index: 1326963 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 3.4061. Min Range: -3.4061

Max Act: 2.3405. Min Act: -0.0000

Data Index: 285037 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 3.4061. Min Range: -3.4061

Max Act: 2.1441. Min Act: -0.0000

Data Index: 7953 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 3.4061. Min Range: -3.4061

Max Act: 2.1431. Min Act: -0.0000

Data Index: 1206555 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 3.4061. Min Range: -3.4061

Max Act: 2.1878. Min Act: -0.0000

Data Index: 828019 (C4 (Web Text))

Max Activating Token Index: 346